Papers › 75 Languages, 1 Model: Parsing Universal Dependencies Universally

75 Languages, 1 Model: Parsing Universal Dependencies Universally

3 Apr 2019IJCNLP 2019 11arXiv:1904.02099archive 2025-07-28

Dan Kondratyuk, Milan Straka

We present UDify, a multilingual multi-task model capable of accurately predicting universal part-of-speech, morphological features, lemmas, and dependency trees simultaneously for all 124 Universal Dependencies treebanks across 75 languages. By leveraging a multilingual BERT self-attention model pretrained on 104 languages, we found that fine-tuning it on all datasets concatenated together with simple softmax classifiers for each UD task can result in state-of-the-art UPOS, UFeats, Lemmas, UAS, and LAS scores, without requiring any recurrent or language-specific components. We evaluate UDify for multilingual learning, showing that low-resource languages benefit the most from cross-linguistic annotations. We also evaluate for zero-shot learning, with results suggesting that multilingual training provides strong UD predictions even for languages that neither UDify nor BERT have ever been trained on. Code for UDify is available at https://github.com/hyperparticle/udify.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 12 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 12 samples from 1 repository, 9 ran (9 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

hyperparticle/udify officialmentioned in papermentioned on GitHubpytorchMITSyntology: 12 samples, 9 ran (0 instrument-failed) · 3 unverified report
ahmetustun/udapter mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to UDapter: Language Adaptation for Truly Universal Dependency Parsing (arXiv:2004.14327; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
idiap/g2g-transformer mentioned on GitHubpytorchGPL-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Transformers as Graph-to-Graph Models (arXiv:2310.17936; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

12 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

9ran
3unverified

Licence: 0 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from hyperparticle/udify. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

hyperparticle/udify official repository 12 samples, 9 ran (0 instrument-failed) · 3 unverified
apply_lemma_rule udify/dataset_readers/lemma_edit.py ran MIT (permissive) · dd23f8f805a509d4 · report fixture: signature form:str/0/str, lemma_rule:str/0/str · returned str · level recorded 2026-09-25
distance in 53 papers
census: 8 implementations from 8 papers, 6 distinct outputs across 3 buckets, one shared input per bucket
udify/dataset_readers/evaluate_2019_task2.py ran fingerprinted MIT (permissive) · 665f20ac94b4aa09 · report fixture: signature str1:str/0/str, str2:str/0/str · returned int · level recorded 2026-09-25
gen_lemma_rule udify/dataset_readers/lemma_edit.py ran fingerprinted MIT (permissive) · d56f4a572f75726c · report fixture: signature form:str/0/str, lemma:str/0/str, allow_copy:bool/0/bool · returned str · level recorded 2026-09-25
get_ud_treebank_files udify/util.py ran MIT (permissive) · 41be2131e0bb7615 · report fixture: signature dataset_dir:str/0/str, treebanks:list/1/str · returned dict · level recorded 2026-09-25
get_ud_treebank_names udify/util.py ran MIT (permissive) · e9c1c9c44d53c7dc · report fixture: signature dataset_dir:str/0/str · returned list · level recorded 2026-09-25
manipulate_data udify/dataset_readers/evaluate_2019_task2.py ran MIT (permissive) · 6b04a2e33ab50ab7 · report fixture: returned tuple · level recorded 2026-09-25
min_edit_script udify/dataset_readers/lemma_edit.py ran fingerprinted MIT (permissive) · 277006db04b14f51 · report fixture: signature source:str/0/str, target:str/0/str, allow_copy:bool/0/bool · returned str · level recorded 2026-09-25
sequence_cross_entropy udify/models/tag_decoder.py ran MIT (permissive) · dff441cf8da0ff92 · report fixture: signature log_probs:Tensor/3/float, targets:Tensor/2/int, weights:Tensor/2/float, average:str/0/str, label_smoothing:NoneType/0/? · returned Tensor · level recorded 2026-09-25
set_equal udify/dataset_readers/evaluate_2019_task2.py ran fingerprinted MIT (permissive) · f5cf6da83aa49097 · report fixture: signature str1:str/0/str, str2:str/0/str · returned bool · level recorded 2026-09-25
evaluate in 514 papers udify/dataset_readers/conll18_ud_eval.py unverified MIT (permissive) · 245d8f594031798b · report
load_conllu in 5 papers udify/dataset_readers/conll18_ud_eval.py unverified MIT (permissive) · 7db5fbed47b0c09d · report
load_conllu_file udify/dataset_readers/conll18_ud_eval.py unverified MIT (permissive) · d6122a3c08a641ad · report

Tasks

Dependency ParsingZero-Shot Learningmodel

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Dependency Parsing French GSD UDify LAS 91.45 #2 of 2 Archive leaderboard report
Dependency Parsing French GSD UDify UAS 93.60 #2 of 2 Archive leaderboard report
Dependency Parsing ParTUT UDify LAS 88.06 #2 of 2 Archive leaderboard report
Dependency Parsing ParTUT UDify UAS 90.55 #2 of 2 Archive leaderboard report
Dependency Parsing Sequoia Treebank UDify LAS 90.05 #2 of 2 Archive leaderboard report
Dependency Parsing Sequoia Treebank UDify UAS 92.53 #2 of 2 Archive leaderboard report
Dependency Parsing Spoken Corpus UDify LAS 80.01 #2 of 2 Archive leaderboard report
Dependency Parsing Spoken Corpus UDify UAS 85.24 #2 of 2 Archive leaderboard report
Dependency Parsing Universal Dependencies UDify LAS 80.43 #2 of 6 Archive leaderboard report
Dependency Parsing Universal Dependencies UDify UAS 85.69 #2 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AdamAttentionAttention DropoutBERTDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSoftmaxWeight DecayWordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections